297565aa22
Modern compilers are perfectly capable of extracting parallelism from the XOR routines, provided that the prototypes reflect the nature of the input accurately, in particular, the fact that the input vectors are expected not to overlap. This is not documented explicitly, but is implied by the interchangeability of the various C routines, some of which use temporary variables while others don't: this means that these routines only behave identically for non-overlapping inputs. So let's decorate these input vectors with the __restrict modifier, which informs the compiler that there is no overlap. While at it, make the input-only vectors pointer-to-const as well. Tested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Link: https://github.com/ClangBuiltLinux/linux/issues/563 Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
739 lines
14 KiB
C
739 lines
14 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
* include/asm-generic/xor.h
|
|
*
|
|
* Generic optimized RAID-5 checksumming functions.
|
|
*/
|
|
|
|
#include <linux/prefetch.h>
|
|
|
|
static void
|
|
xor_8regs_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0];
|
|
p1[1] ^= p2[1];
|
|
p1[2] ^= p2[2];
|
|
p1[3] ^= p2[3];
|
|
p1[4] ^= p2[4];
|
|
p1[5] ^= p2[5];
|
|
p1[6] ^= p2[6];
|
|
p1[7] ^= p2[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_8regs_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0] ^ p3[0];
|
|
p1[1] ^= p2[1] ^ p3[1];
|
|
p1[2] ^= p2[2] ^ p3[2];
|
|
p1[3] ^= p2[3] ^ p3[3];
|
|
p1[4] ^= p2[4] ^ p3[4];
|
|
p1[5] ^= p2[5] ^ p3[5];
|
|
p1[6] ^= p2[6] ^ p3[6];
|
|
p1[7] ^= p2[7] ^ p3[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_8regs_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
|
|
p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
|
|
p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
|
|
p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
|
|
p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
|
|
p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
|
|
p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
|
|
p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_8regs_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
|
|
p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
|
|
p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
|
|
p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
|
|
p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
|
|
p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
|
|
p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
|
|
p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
p5 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_32regs_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_32regs_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
d0 ^= p3[0];
|
|
d1 ^= p3[1];
|
|
d2 ^= p3[2];
|
|
d3 ^= p3[3];
|
|
d4 ^= p3[4];
|
|
d5 ^= p3[5];
|
|
d6 ^= p3[6];
|
|
d7 ^= p3[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_32regs_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
d0 ^= p3[0];
|
|
d1 ^= p3[1];
|
|
d2 ^= p3[2];
|
|
d3 ^= p3[3];
|
|
d4 ^= p3[4];
|
|
d5 ^= p3[5];
|
|
d6 ^= p3[6];
|
|
d7 ^= p3[7];
|
|
d0 ^= p4[0];
|
|
d1 ^= p4[1];
|
|
d2 ^= p4[2];
|
|
d3 ^= p4[3];
|
|
d4 ^= p4[4];
|
|
d5 ^= p4[5];
|
|
d6 ^= p4[6];
|
|
d7 ^= p4[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_32regs_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
d0 ^= p3[0];
|
|
d1 ^= p3[1];
|
|
d2 ^= p3[2];
|
|
d3 ^= p3[3];
|
|
d4 ^= p3[4];
|
|
d5 ^= p3[5];
|
|
d6 ^= p3[6];
|
|
d7 ^= p3[7];
|
|
d0 ^= p4[0];
|
|
d1 ^= p4[1];
|
|
d2 ^= p4[2];
|
|
d3 ^= p4[3];
|
|
d4 ^= p4[4];
|
|
d5 ^= p4[5];
|
|
d6 ^= p4[6];
|
|
d7 ^= p4[7];
|
|
d0 ^= p5[0];
|
|
d1 ^= p5[1];
|
|
d2 ^= p5[2];
|
|
d3 ^= p5[3];
|
|
d4 ^= p5[4];
|
|
d5 ^= p5[5];
|
|
d6 ^= p5[6];
|
|
d7 ^= p5[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
p5 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_8regs_p_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
|
|
do {
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
once_more:
|
|
p1[0] ^= p2[0];
|
|
p1[1] ^= p2[1];
|
|
p1[2] ^= p2[2];
|
|
p1[3] ^= p2[3];
|
|
p1[4] ^= p2[4];
|
|
p1[5] ^= p2[5];
|
|
p1[6] ^= p2[6];
|
|
p1[7] ^= p2[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static void
|
|
xor_8regs_p_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
prefetch(p3);
|
|
|
|
do {
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
prefetch(p3+8);
|
|
once_more:
|
|
p1[0] ^= p2[0] ^ p3[0];
|
|
p1[1] ^= p2[1] ^ p3[1];
|
|
p1[2] ^= p2[2] ^ p3[2];
|
|
p1[3] ^= p2[3] ^ p3[3];
|
|
p1[4] ^= p2[4] ^ p3[4];
|
|
p1[5] ^= p2[5] ^ p3[5];
|
|
p1[6] ^= p2[6] ^ p3[6];
|
|
p1[7] ^= p2[7] ^ p3[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static void
|
|
xor_8regs_p_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
prefetch(p3);
|
|
prefetch(p4);
|
|
|
|
do {
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
prefetch(p3+8);
|
|
prefetch(p4+8);
|
|
once_more:
|
|
p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
|
|
p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
|
|
p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
|
|
p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
|
|
p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
|
|
p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
|
|
p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
|
|
p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static void
|
|
xor_8regs_p_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
prefetch(p3);
|
|
prefetch(p4);
|
|
prefetch(p5);
|
|
|
|
do {
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
prefetch(p3+8);
|
|
prefetch(p4+8);
|
|
prefetch(p5+8);
|
|
once_more:
|
|
p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
|
|
p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
|
|
p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
|
|
p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
|
|
p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
|
|
p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
|
|
p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
|
|
p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
p5 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static void
|
|
xor_32regs_p_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
once_more:
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static void
|
|
xor_32regs_p_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
prefetch(p3);
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
prefetch(p3+8);
|
|
once_more:
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
d0 ^= p3[0];
|
|
d1 ^= p3[1];
|
|
d2 ^= p3[2];
|
|
d3 ^= p3[3];
|
|
d4 ^= p3[4];
|
|
d5 ^= p3[5];
|
|
d6 ^= p3[6];
|
|
d7 ^= p3[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static void
|
|
xor_32regs_p_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
prefetch(p3);
|
|
prefetch(p4);
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
prefetch(p3+8);
|
|
prefetch(p4+8);
|
|
once_more:
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
d0 ^= p3[0];
|
|
d1 ^= p3[1];
|
|
d2 ^= p3[2];
|
|
d3 ^= p3[3];
|
|
d4 ^= p3[4];
|
|
d5 ^= p3[5];
|
|
d6 ^= p3[6];
|
|
d7 ^= p3[7];
|
|
d0 ^= p4[0];
|
|
d1 ^= p4[1];
|
|
d2 ^= p4[2];
|
|
d3 ^= p4[3];
|
|
d4 ^= p4[4];
|
|
d5 ^= p4[5];
|
|
d6 ^= p4[6];
|
|
d7 ^= p4[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static void
|
|
xor_32regs_p_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8 - 1;
|
|
|
|
prefetchw(p1);
|
|
prefetch(p2);
|
|
prefetch(p3);
|
|
prefetch(p4);
|
|
prefetch(p5);
|
|
|
|
do {
|
|
register long d0, d1, d2, d3, d4, d5, d6, d7;
|
|
|
|
prefetchw(p1+8);
|
|
prefetch(p2+8);
|
|
prefetch(p3+8);
|
|
prefetch(p4+8);
|
|
prefetch(p5+8);
|
|
once_more:
|
|
d0 = p1[0]; /* Pull the stuff into registers */
|
|
d1 = p1[1]; /* ... in bursts, if possible. */
|
|
d2 = p1[2];
|
|
d3 = p1[3];
|
|
d4 = p1[4];
|
|
d5 = p1[5];
|
|
d6 = p1[6];
|
|
d7 = p1[7];
|
|
d0 ^= p2[0];
|
|
d1 ^= p2[1];
|
|
d2 ^= p2[2];
|
|
d3 ^= p2[3];
|
|
d4 ^= p2[4];
|
|
d5 ^= p2[5];
|
|
d6 ^= p2[6];
|
|
d7 ^= p2[7];
|
|
d0 ^= p3[0];
|
|
d1 ^= p3[1];
|
|
d2 ^= p3[2];
|
|
d3 ^= p3[3];
|
|
d4 ^= p3[4];
|
|
d5 ^= p3[5];
|
|
d6 ^= p3[6];
|
|
d7 ^= p3[7];
|
|
d0 ^= p4[0];
|
|
d1 ^= p4[1];
|
|
d2 ^= p4[2];
|
|
d3 ^= p4[3];
|
|
d4 ^= p4[4];
|
|
d5 ^= p4[5];
|
|
d6 ^= p4[6];
|
|
d7 ^= p4[7];
|
|
d0 ^= p5[0];
|
|
d1 ^= p5[1];
|
|
d2 ^= p5[2];
|
|
d3 ^= p5[3];
|
|
d4 ^= p5[4];
|
|
d5 ^= p5[5];
|
|
d6 ^= p5[6];
|
|
d7 ^= p5[7];
|
|
p1[0] = d0; /* Store the result (in bursts) */
|
|
p1[1] = d1;
|
|
p1[2] = d2;
|
|
p1[3] = d3;
|
|
p1[4] = d4;
|
|
p1[5] = d5;
|
|
p1[6] = d6;
|
|
p1[7] = d7;
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
p5 += 8;
|
|
} while (--lines > 0);
|
|
if (lines == 0)
|
|
goto once_more;
|
|
}
|
|
|
|
static struct xor_block_template xor_block_8regs = {
|
|
.name = "8regs",
|
|
.do_2 = xor_8regs_2,
|
|
.do_3 = xor_8regs_3,
|
|
.do_4 = xor_8regs_4,
|
|
.do_5 = xor_8regs_5,
|
|
};
|
|
|
|
static struct xor_block_template xor_block_32regs = {
|
|
.name = "32regs",
|
|
.do_2 = xor_32regs_2,
|
|
.do_3 = xor_32regs_3,
|
|
.do_4 = xor_32regs_4,
|
|
.do_5 = xor_32regs_5,
|
|
};
|
|
|
|
static struct xor_block_template xor_block_8regs_p __maybe_unused = {
|
|
.name = "8regs_prefetch",
|
|
.do_2 = xor_8regs_p_2,
|
|
.do_3 = xor_8regs_p_3,
|
|
.do_4 = xor_8regs_p_4,
|
|
.do_5 = xor_8regs_p_5,
|
|
};
|
|
|
|
static struct xor_block_template xor_block_32regs_p __maybe_unused = {
|
|
.name = "32regs_prefetch",
|
|
.do_2 = xor_32regs_p_2,
|
|
.do_3 = xor_32regs_p_3,
|
|
.do_4 = xor_32regs_p_4,
|
|
.do_5 = xor_32regs_p_5,
|
|
};
|
|
|
|
#define XOR_TRY_TEMPLATES \
|
|
do { \
|
|
xor_speed(&xor_block_8regs); \
|
|
xor_speed(&xor_block_8regs_p); \
|
|
xor_speed(&xor_block_32regs); \
|
|
xor_speed(&xor_block_32regs_p); \
|
|
} while (0)
|